CN110718282A - Packaging food identification method and device - Google Patents
Packaging food identification method and device Download PDFInfo
- Publication number
- CN110718282A CN110718282A CN201910975127.8A CN201910975127A CN110718282A CN 110718282 A CN110718282 A CN 110718282A CN 201910975127 A CN201910975127 A CN 201910975127A CN 110718282 A CN110718282 A CN 110718282A
- Authority
- CN
- China
- Prior art keywords
- information
- health
- food
- target user
- ingredient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Nutrition Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a method and a device for identifying packaged food, wherein the method comprises the following steps: acquiring a packaging picture of food to be identified, and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model; identifying each line of character areas in the ingredient information area and/or the nutrient component information area through a character area identification model established by pre-training; identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutritional ingredient information of the food; and acquiring health information of a target user, and judging whether the food has a risk of influencing the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information. By applying the scheme provided by the invention, the problem that a user cannot accurately judge whether the food is suitable for eating by himself or herself in the prior art can be solved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for identifying packaged food, electronic equipment and a computer readable storage medium.
Background
At present, the types and the forms of food are various, and common users can not accurately judge whether the current food is suitable for being eaten by themselves or not before eating the packaged food, and whether diseases or health conditions of the users are influenced or not.
For example, contraindicated foods for diabetics include, but are not limited to, fried pork chops, fried chicken and meats, creams, chocolates, honey, desserts, and the like, namely: the diabetic is contraindicated for eating the food with high oil content, high cholesterol content, high sugar content and high starch content. Contraindicated foods for patients with hypertension include but are not limited to streaky pork, bacon, sausage, shallot, garlic, pepper, etc., namely: the patients with hypertension are prohibited from eating meat with high fat content, food with pungent and pungent taste, and pickled food with high salt content. Contraindicated foods for heart disease patients include, but are not limited to, bacon, beef, sausage, chicken liver, sheep liver, pig lung, pig brain, pig large intestine, etc., namely: the patients with heart diseases are prohibited from eating spicy food, high-fat and high-cholesterol food and high-salt pickled food. Contraindicated foods for obese patients include, but are not limited to, fried steamed bread, fried broiler chickens, beans, sweet potatoes, lotus root starch, honey, chocolate, desserts, and the like, namely: the obesity patients are contraindicated for eating food containing fat, protein and high sugar content.
Therefore, the contraindicated food for each disease is more in variety, and when one person suffers from a plurality of diseases, the corresponding contraindicated food is more. Moreover, the health conditions of different people are greatly different, different standards can be provided under the conditions of different ages, sexes, heights, weights and the like, if the users simply analyze whether the ingredients or the nutrient composition list printed on the package contain contraindication foods, the common users are troublesome, and the ingredients and the nutrient composition containing more professional nouns and expression of a plurality of similar words are easy to cause confusion. Therefore, in the prior art, it is difficult for a user to accurately judge whether the food is suitable for the user to eat, so that a scheme capable of accurately judging whether the food is suitable for the user to eat is needed.
Disclosure of Invention
The invention aims to provide a method and a device for identifying packaged food, electronic equipment and a computer readable storage medium, which are used for solving the problem that a user cannot accurately judge whether the food is suitable for eating by himself or herself in the prior art. The specific technical scheme is as follows:
in a first aspect, the present invention provides a method for identifying a packaged food, including:
acquiring a packaging picture of food to be identified, and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model;
identifying each line of character areas in the ingredient information area and/or the nutrient component information area through a character area identification model established by pre-training;
identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutritional ingredient information of the food;
and acquiring health information of a target user, and judging whether the food has a risk of influencing the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
Optionally, judging whether the food affects the risk of the health of the target user according to the ingredient information and/or the nutritional ingredient information and the health information, including:
determining keywords influencing the health state of the target user according to the health information;
searching in the ingredient information and/or the nutritional ingredient information, and judging whether ingredients and/or nutritional ingredients matched with the keywords exist or not;
if so, determining that the food product is at risk of affecting the health status of the target user;
if not, determining that the food is not at risk of affecting the health status of the target user.
Optionally, determining keywords affecting the health status of the target user according to the health information includes:
processing the health information by adopting a synonym model trained and established in advance to acquire standard health information of the target user, wherein the synonym model is acquired by a natural language understanding method;
and acquiring a keyword mapped with the standard health information of the target user according to the mapping relation between the standard health information and the keyword, wherein the keyword is used as the keyword influencing the health state of the target user, and the mapping relation between the standard health information and the keyword is stored in a database in advance.
Optionally, searching the ingredient information and/or the nutritional ingredient information to determine whether there are ingredients and/or nutritional ingredients matching the keyword, including:
converting the ingredient information into standard word information by adopting a synonym model trained and established in advance, wherein the synonym model is obtained by a natural language understanding method;
searching in standard word information and/or nutrient component information corresponding to the ingredient information, and judging whether ingredients and/or nutrient components matched with the keywords exist.
Optionally, the health information includes disease information and/or physical sign information of the user, where the disease information includes: the disease that the user has suffered from or the disease that the user is more concerned about suffering from, the sign information comprises: symptoms of recent discomfort and information on the sex, age, height, weight, heart rate, blood pressure, blood glucose, body fat rate of the user.
Optionally, the method further includes:
setting a weight value through a weight setting model established by pre-training according to the sign information of the target user;
according to the weight value, calculating a safe intake threshold value of ingredients and/or nutritional ingredients influencing the health state of the target user in the food through a preset calculation formula;
determining the edible amount of the target user to the food according to the safe intake threshold value and the content of the ingredients and/or nutritional components influencing the health state of the target user in the food.
Optionally, the method further includes:
prompting the target user that the food item is not edible, or is not edible beyond the determined edible amount.
Optionally, the weight setting model is obtained by training with different disease information and sign information as condition inputs.
Optionally, the calculation formula is stored in a database, and is mapped and stored with corresponding disease information and/or physical sign information.
Optionally, the obtaining health information of the target user includes:
acquiring health information of the target user through a health database, wherein the health database is established in the following way: identifying a physical examination report, a medical record report and/or a laboratory sheet uploaded by a user, establishing a health database after acquiring health information of the user, or establishing the health database after receiving the health information input by the user;
and/or receiving the health information input by the target user through a human-computer interaction interface;
and/or acquiring the health information of the target user through a wearable intelligent device worn by the target user.
Optionally, the region identification model is an attention model established by using an attention mechanism;
or, the region identification model is a convolutional neural network model.
Optionally, the character region recognition model is a Mask-RCNN model.
Optionally, the method further includes:
judging whether the food contains the dietetic restraint components and/or the allergy information according to the ingredient information and/or the nutritional component information;
if so, prompting the target user for the presence of a dietetic composition and/or allergy information in the food.
In a second aspect, the present invention further provides a packaged food identification device, including:
the first identification module is used for acquiring a packaging picture of food to be identified and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model;
the second recognition module is used for recognizing each line of character area in the ingredient information area and/or the nutrient component information area through a character area recognition model established by pre-training;
the third identification module is used for identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutrient component information of the food;
and the judging module is used for acquiring the health information of the target user and judging whether the food affects the risk of the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
Optionally, the determining module is specifically configured to:
determining keywords influencing the health state of the target user according to the health information;
searching in the ingredient information and/or the nutritional ingredient information, and judging whether ingredients and/or nutritional ingredients matched with the keywords exist or not;
if so, determining that the food product is at risk of affecting the health status of the target user;
if not, determining that the food is not at risk of affecting the health status of the target user.
Optionally, the determining module determines keywords affecting the health status of the target user according to the health information, including:
processing the health information by adopting a synonym model trained and established in advance to acquire standard health information of the target user, wherein the synonym model is acquired by a natural language understanding method;
and acquiring a keyword mapped with the standard health information of the target user according to the mapping relation between the standard health information and the keyword, wherein the keyword is used as the keyword influencing the health state of the target user, and the mapping relation between the standard health information and the keyword is stored in a database in advance.
Optionally, the determining module searches the ingredient information and/or the nutritional ingredient information to determine whether there are ingredients and/or nutritional ingredients matching the keyword, including:
converting the ingredient information into standard word information by adopting a synonym model trained and established in advance, wherein the synonym model is obtained by a natural language understanding method;
searching in standard word information and/or nutrient component information corresponding to the ingredient information, and judging whether ingredients and/or nutrient components matched with the keywords exist.
Optionally, the health information includes disease information and/or physical sign information of the user, where the disease information includes: the disease that the user has suffered from or the disease that the user is more concerned about suffering from, the sign information comprises: symptoms of recent discomfort and information on the sex, age, height, weight, heart rate, blood pressure, blood glucose, body fat rate of the user.
Optionally, the apparatus further comprises:
the setting module is used for setting a weight value through a weight setting model established by pre-training according to the sign information of the target user;
the calculation module is used for calculating the safe intake threshold of ingredients and/or nutritional ingredients influencing the health state of the target user in the food according to the weight value through a preset calculation formula;
a determination module for determining the edible amount of the food product by the target user according to the safe intake threshold value and the content of ingredients and/or nutritional components in the food product which affect the health state of the target user.
Optionally, the apparatus further comprises:
a prompt module for prompting the target user that the food item is inedible or inedible beyond the determined edible amount.
Optionally, the weight setting model is obtained by training with different disease information and sign information as condition inputs.
Optionally, the calculation formula is stored in a database, and is mapped and stored with corresponding disease information and/or physical sign information.
Optionally, the obtaining, by the determining module, health information of the target user includes:
acquiring health information of the target user through a health database, wherein the health database is established in the following way: identifying a physical examination report, a medical record report and/or a laboratory sheet uploaded by a user, establishing a health database after acquiring health information of the user, or establishing the health database after receiving the health information input by the user;
and/or receiving the health information input by the target user through a human-computer interaction interface;
and/or acquiring the health information of the target user through a wearable intelligent device worn by the target user.
Optionally, the region identification model is an attention model established by using an attention mechanism;
or, the region identification model is a convolutional neural network model.
Optionally, the character region recognition model is a Mask-RCNN model.
Optionally, the determining module is further configured to:
judging whether the food contains the dietetic restraint components and/or the allergy information according to the ingredient information and/or the nutritional component information;
if so, prompting the target user for the presence of a dietetic composition and/or allergy information in the food.
In a third aspect, the present invention further provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement the steps of the method for identifying packaged food according to the first aspect when executing the program stored in the memory.
In a fourth aspect, the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method for identifying a packaged food item according to the first aspect.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
the method and the device can identify the packaging picture of the food, acquire the ingredient information and/or the nutritional ingredient information displayed on the food package, judge whether the ingredient information and/or the nutritional ingredient information of the food contains ingredients which influence the health of the user or not based on the health information of the user, and further determine whether the food has risks which influence the health state of the user or not, so that the health prompt of the user can be performed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying packaged food according to an embodiment of the present invention;
FIG. 2 is a flow chart of the method of FIG. 1 for determining whether a food product is at risk of affecting the health status of a target user;
fig. 3 is a schematic structural diagram of a packaged food identification device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following provides a method and an apparatus for identifying packaged food, an electronic device and a computer-readable storage medium according to the present invention, and is described in detail with reference to the accompanying drawings and specific embodiments. Advantages and features of the present invention will become apparent from the following description and from the claims. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention.
In order to solve the problems in the prior art, embodiments of the present invention provide a method and an apparatus for identifying a packaged food, an electronic device, and a computer-readable storage medium.
The method for identifying a packaged food according to the embodiment of the present invention is applicable to a packaged food identification device according to the embodiment of the present invention, and the packaged food identification device may be configured on an electronic device. The electronic device may be a personal computer, a mobile terminal, and the like, and the mobile terminal may be a hardware device having various operating systems, such as a mobile phone and a tablet computer.
Fig. 1 is a schematic flow chart of a method for identifying packaged food according to an embodiment of the present invention. Referring to fig. 1, a method for identifying a packaged food may include the following steps:
step S101, obtaining a packaging picture of food to be identified, and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model.
For example, a package bag of a food to be identified may be photographed by a mobile phone to obtain a package picture, where the package picture needs to include an ingredient information area and/or a nutritional component information area of the food. Specifically, the ingredient information area and/or the nutritional ingredient information area can be shot in a targeted manner, so that the ingredient information area and/or the nutritional ingredient information area in the package picture are clear and convenient to identify.
The region identification model may be an attention model established using an attention mechanism. An Attention Model (Attention Model) is built by adopting an Attention Mechanism (Attention Mechanism), an area with higher weight is obtained after sample training, namely an ingredient information area and/or a nutritional ingredient information area, the training process is to input various food packaging pictures marked with the ingredient information area and/or the nutritional ingredient information area, the Model can set higher weight for the ingredient information area and/or the nutritional ingredient information area, namely an Attention area, so that other irrelevant area information, such as interference information of figures, backgrounds and the like, is ignored.
In other embodiments, the region identification model may also be a convolutional neural network model. The method comprises the steps of training an area recognition model by adopting a convolutional neural network, carrying out sample training by marking each area (including an ingredient information area and/or a nutrient component information area) on a packaging picture in advance, marking the positions of different areas by the established area recognition model by utilizing multi-target detection (detection), and marking the ingredient information area and/or the nutrient component information area for further processing.
And S102, identifying each line of character area in the ingredient information area and/or the nutrient component information area through a character area identification model trained and established in advance.
In this embodiment, the character region identification model is a Mask-RCNN model. The Mask-RCNN is an improved algorithm of the fast-RCNN, and can identify a text area of each segmented line or small area in an ingredient information area and/or a nutrient information area on a food packaging picture, divide the text area into different Mask areas, obtain a Mask, and mark the position of each Mask area through a circumscribed rectangle (namely, a classification regression idea).
It can be understood that the ingredient information and the nutritional ingredient information in the ingredient information area and the nutritional ingredient information area may have various forms, for example, multiple lines, intervals between lines, parallel segmentation of other information (for example, information of manufacturers, storage methods, shelf lives, and the like), or a curved form such as a cylindrical form when being packaged causes characters to have radians, and these character areas can be completely marked by adopting a Mask-RCNN model for identification, thereby avoiding an error in character area identification.
And S103, identifying characters in each line of character area through a character identification model to obtain ingredient information and/or nutritional ingredient information of the food.
The character recognition model may be a model built based on a hole convolution and an attention model. Specifically, the recognizing the characters in each line of the character region by using the pre-trained character recognition model may include: the character recognition model adopts hole convolution to extract the characteristics of the picture of each character area; and decoding the extracted features into characters through the attention model to obtain the character content in each character area. Then, the recognized characters are combined and sorted according to the sequence of the character areas, and ingredient information and/or nutritional ingredient information of the food can be obtained.
And step S104, acquiring health information of a target user, and judging whether the food affects the risk of the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
The health information of the user may include disease information and/or physical sign information of the user, wherein the disease information includes: the disease that the user has suffered from or the disease that the user is more concerned about suffering from, the sign information comprises: the recent uncomfortable symptoms and the information of the sex, age, height, weight, heart rate, blood pressure, blood sugar and body fat rate of the user may also include other information, which is not limited in this embodiment.
Specifically, the health information of the target user may be obtained in the following manner:
a. acquiring health information of the target user through a health database, wherein the health database is established in the following way: identifying a physical examination report, a medical record report and/or a laboratory sheet uploaded by a user, establishing a health database after acquiring health information of the user, or establishing the health database after receiving the health information input by the user;
b. receiving health information input by the target user through a human-computer interaction interface;
c. and acquiring the health information of the target user through the wearable intelligent equipment worn by the target user.
In the mode a, the health database is stored in the cloud, the data can be obtained by a physical examination report, various examination or laboratory test reports uploaded by a user, the system identifies the report and document information through a model established by pre-training and obtains the health information of the user after the report and document information are collated, and then the health database is created, or the health database can be created after the relevant health data input by the user are collated.
For the mode b, the user inputs own health information by temporarily performing text input or voice input on a software interface, for example, the user inputs information such as diabetes, cold, oral ulcer and the like, and corresponding processing can be performed on non-standard health information input by the user, for example, the input information is converted into standard health information according to a synonym model obtained by pre-training, wherein the synonym model is obtained by a natural language understanding method, similar health information is unified into standard input, for example, the user inputs diabetes, hyperglycemia or can not eat sugar and the like, and the similar health information can be uniformly processed into standard word records, for example, the synonym model is uniformly recorded as hyperglycemia.
For the method c, health information of the user, such as heart rate, blood pressure, body fat rate, and the like, can be acquired through a wearable smart device worn by the user, such as an electronic bracelet, an electronic watch, and the like, and the information may also affect the intake of food ingredients.
In practical application, the health information of the target user may be obtained in any one of the above manners, may also be obtained by combining any two manners, and may also be combined with the health information of the target user in three manners, which is not limited in this embodiment.
A specific implementation manner of determining whether the food has an impact on the risk of the target user' S health in step S104 will be described in detail below.
As shown in fig. 2, the step S104 of determining whether the food has a risk of affecting the health status of the target user according to the ingredient information and/or the nutritional component information and the health information includes the following steps:
s41, determining keywords influencing the health state of the target user according to the health information;
s42, searching in the ingredient information and/or the nutrient component information, and judging whether ingredients and/or nutrient components matched with the keywords exist; if so, performing S43, and if not, performing S44;
s43, judging the risk that the food affects the health state of the target user;
and S44, judging that the food has no risk of influencing the health state of the target user.
Specifically, in step S41, determining keywords affecting the health status of the target user according to the health information includes: firstly, processing the health information by adopting a synonym model trained and established in advance to acquire standard health information of the target user, wherein the synonym model is acquired by a natural language understanding method; and then, acquiring a keyword mapped with the standard health information of the target user according to the mapping relation between the standard health information and the keyword, wherein the keyword is used as the keyword influencing the health state of the target user, and the mapping relation between the standard health information and the keyword is stored in a database in advance.
For example, if the health information of the target user is diabetes or the target user cannot eat sugar, the synonym model is used for processing the health information, the health information can be processed into standard health information, for example, the health information is uniformly recorded as blood sugar level, and the standard health information of the target user is obtained as blood sugar level.
The mapping relationship between the standard health information and the keyword is a preset standard, and is stored in a standard database, for example, the mapping between blood glucose level and the keyword "sugar", the mapping between blood pressure level and the keyword "salt", the mapping between oral ulcer and the keyword "spicy stimulation", and the like. After the standard health information of the target user is obtained, the standard database can be inquired to find out the mapped keywords as the keywords influencing the health state of the target user. For example, if the standard health information of the target user is hyperglycemia, the keyword affecting the health status of the target user may be determined to be "sugar" by querying the standard database. In addition, in practical applications, the same standard health information can be mapped with a plurality of keywords, for example, the blood pressure can be mapped with two keywords of "salt" and "fat".
In step S42, searching in the ingredient information and/or nutritional component information, and determining whether there is an ingredient and/or nutritional component matching the keyword, specifically including: firstly, converting the ingredient information into standard word information by adopting a synonym model trained and established in advance, wherein the synonym model is obtained by a natural language understanding method; and then searching in standard word information and/or nutrient component information corresponding to the ingredient information, and judging whether ingredients and/or nutrient components matched with the keywords exist.
Because the ingredients may have non-standard phrases or similar words, corresponding conversion processing is required, the ingredient information is converted into standard word information according to a synonym model obtained by pre-training, similar ingredient information is unified into standard words, for example, white granulated sugar, brown sugar, rock sugar and maltose are all uniformly converted into sugar, if xylitol is, the similar ingredient information is labeled as special sugar, and vegetable oil, butter and cream are all uniformly converted into fat.
For example, if the keyword is "sugar", searching in standard word information and/or nutritional ingredient information corresponding to the ingredient information according to the keyword, if there is an ingredient and/or nutritional ingredient "sugar" matching with "sugar", determining that the food has a risk of affecting the health status of the target user, and if not, determining that the food has no risk of affecting the health status of the target user. When the risk that the food affects the health state is judged, the risk can be obviously prompted to the user.
In addition, if the ingredient contains a component, it is also equivalent to containing such a component, for example, if the ingredient contains fruits such as apple, the ingredient is considered to contain a sugar component, and if the ingredient contains kelp or laver, the ingredient is considered to contain a salt component. Therefore, in order to solve the above problem, it is also necessary to convert the substances in the ingredient information into the standard word information by using the synonym model, that is, convert "apple" in the ingredient into the standard word information "sugar" and convert "kelp and laver" in the ingredient into the standard word information "salt". In practical application, standard word information corresponding to ingredients can be searched from a data table, wherein the data table records the corresponding relationship between the names of the substances in different ingredients and the standard words, for example, the data table records that the standard words corresponding to the substances "apple" are "sugar", and the standard words corresponding to the substances "kelp" and "laver" are "salt".
In practical application, whether certain food has risks affecting health conditions or not can be comprehensively judged according to various health information of target users. For example, if the user has diarrhea recently, light food should be selected, if the health data shows that the user has oral ulcer recently, spicy stimulating food is avoided, and whether the food is suitable for eating is judged according to the physical data of the user, for example, whether children, women in physiology, old people, pregnant women, obese people (comprehensively judged according to height, weight and age) or other symptoms with discomfort recently are comprehensively judged, whether certain food is suitable for eating or the amount of food is comprehensively judged, and the eating standards of different people and different body states are different.
Further, even if it is determined that the food is at risk of affecting the health status, if the health status of the user is still acceptable, the user may be allowed to eat a certain amount of the food, but the edible amount of the user on the food needs to be calculated to avoid the health problem caused by too much eating of the user. Specifically, the method provided by the present invention may further include:
setting a weight value through a weight setting model established by pre-training according to the sign information of the target user;
according to the weight value, calculating a safe intake threshold value of ingredients and/or nutritional ingredients influencing the health state of the target user in the food through a preset calculation formula;
determining the edible amount of the target user to the food according to the safe intake threshold value and the content of the ingredients and/or nutritional components influencing the health state of the target user in the food.
Specifically, the weight value is set according to the physical sign information such as the gender and age of the user, for example, different ages and genders may cause different ranges of standard blood glucose concentration, so that the sugar content that can be ingested is different, when the food shot and identified by the target user contains sugar, the weight value is set according to the physical sign information of the target user, so that the threshold value of the sugar content that can be ingested by the target user is calculated, and whether the user can eat or eat the amount is judged according to the sugar content of the current food.
The setting of the weight values is set by a pre-trained weight setting model, which is obtained by training with different disease information and sign information as condition input, for example, the weight setting model is established by the condition input training of different sexes, ages, heights, weights and other special conditions. The disease information further includes blood glucose concentration of diabetic patients, blood pressure value of hypertensive patients, heart rate of heart patients, obesity index data of obese patients, etc., and can be considered individually in different cases.
For example, a certain user has diabetes and is mapped to a keyword 'sugar', a weight value is set to be A through a weight setting model according to the physical sign information of the user, a calculation formula of a sugar influence value is set to be A (age x height)/(weight x blood sugar concentration), so that a safety threshold value of the current user for taking the sugar is calculated, and whether the current user can eat or the number of the users can be calculated according to the content of the sugar in the identified food. The calculation formula for associating each disease or health condition with each component is stored in a database through mapping and is mapped and stored with corresponding disease information and/or physical sign information.
When the ingredients which influence the health of the user or the content of a certain substance in the nutritional ingredients in the food exceeds a safe intake threshold value, the user is obviously reminded of forbidding eating, or the user is reminded of relevant information that the edible quantity does not exceed the threshold value, such as that the user has hypertension and needs to eat low-salt food, and if the salt content in the certain food is higher, the user is reminded of not eating as much as possible or eating the quantity which does not exceed one bag, one can, one box, one bottle and the like.
In practical application, if a plurality of influencing components exist for a certain disease or health condition, the contents of the various components in the food are respectively and independently judged, and the reminding is carried out as long as any one of the influencing components exceeds a safety threshold. Similarly, if the user has a plurality of diseases or health conditions, whether each component in the food meets the standard is independently judged for each condition, and any component exceeds the threshold value is prompted.
Further, whether the food contains the dietetic restraint ingredients and/or the allergy information can be judged according to the ingredient information and/or the nutritional ingredient information; if so, prompting the target user for the presence of a dietetic composition and/or allergy information in the food. For example, if the cephalosporin cannot be taken simultaneously with the alcohol-containing food, and it is determined that alcohol is present in the food, the target user is prompted that alcohol, which is a contraindicated ingredient, is present in the food and the cephalosporin cannot be taken simultaneously. Secondly, some ingredient information and/or nutrient component information of the food can directly display allergen information contained in the food, such as milk allergy, nut allergy, fish and shrimp seafood allergy and the like, so that many food packaging bags have printed characters to remind the allergen information, such as' allergen information: the product contains dairy products and allergen information: contains wheat, egg products and dairy products, and the allergen information: contains wheat, soybean, etc., and therefore, it is necessary to present allergy information in food to the user. In addition, if the ingredient information and/or the nutrient information does not directly indicate the allergen information, it is possible to determine whether or not the food contains an allergen from the ingredients and/or the nutrient contained in the food, for example, if the ingredients contain ingredients with similar names such as milk or cow milk, the food may be allergic to milk, if the ingredients contain nuts that are liable to cause allergy such as peanuts and walnuts, the food may be allergic, and if the ingredients contain ingredients such as fish, shrimp, seafood, etc., the food may be allergic, and therefore, if it is determined from the ingredient and nutrient information that the allergen information exists, it is necessary to present the allergen information to the user.
In practical application, after a packaging picture of a certain food is obtained and ingredient information and/or nutrient component information is identified, which people the food is not suitable for eating can be analyzed according to ingredients and nutrient components contained in the food, so that which people the food is not suitable for can be prompted to a user. For example, for a food product, like a user, the food product is not suitable for the following group of people: soybean allergy, gluten intolerance, constipation, osteoporosis, obesity, heart disease, and diarrhea.
Secondly, key components having a large influence on health in the component information can be explained for ingredients or nutritional components contained in a certain food, so that a user can understand why the key components affect health. For example, in the case of a component such as palm oil, the user may be prompted that "this component contains saturated fatty acids or trans fatty acids, and the obese should reduce the intake of harmful fats".
Thirdly, aiming at ingredients or nutritional ingredients contained in a certain food, the content of each ingredient can be calculated, and whether the food is suitable for eating or not is prompted to a user according to the content of each ingredient. For example, if a food product contains 1g of saturated fatty acids and the content of saturated fatty acids is 21%, the user may be informed that the food product contains high saturated fatty acids, which may increase the risk of chronic diseases. For another example, a food product containing 95mg of sodium at a sodium content of 4% by calculation may indicate to the user that the food product contains normal sodium and that a low sodium diet is beneficial for health.
In summary, the method for identifying the packaged food provided by this embodiment can identify the packaging picture of the food, obtain the ingredient information and/or the nutritional ingredient information displayed on the food package, and judge whether the ingredient information and/or the nutritional ingredient information of the food contains ingredients that affect the health of the user based on the health information of the user, so as to determine whether the food has risks that affect the health state of the user, thereby performing health prompt on the user.
Corresponding to the method embodiment, the embodiment of the invention also provides a packaged food identification device. Referring to fig. 3, fig. 3 is a schematic structural diagram of a packaged food identification device according to an embodiment of the present invention, where the packaged food identification device includes:
the first identification module 201 is used for acquiring a packaging picture of food to be identified, and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model;
the second recognition module 202 is configured to recognize each line of character regions in the ingredient information region and/or the nutritional ingredient information region through a character region recognition model established through pre-training;
the third identification module 203 is used for identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutrient component information of the food;
the judging module 204 is configured to obtain health information of a target user, and judge whether the food affects the risk of the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
The packaging type food recognition device provided by the embodiment can recognize the packaging picture of food, acquire ingredient information and/or nutritional ingredient information displayed on a food package, judge whether ingredients influencing the health of a user are contained in the ingredient information and/or the nutritional ingredient information of the food based on the health information of the user, and further determine whether the food has risks influencing the health state of the user, so that health prompt can be performed on the user.
Optionally, the determining module 204 is specifically configured to:
determining keywords influencing the health state of the target user according to the health information;
searching in the ingredient information and/or the nutritional ingredient information, and judging whether ingredients and/or nutritional ingredients matched with the keywords exist or not;
if so, determining that the food product is at risk of affecting the health status of the target user;
if not, determining that the food is not at risk of affecting the health status of the target user.
Optionally, the determining module 204 determines keywords affecting the health status of the target user according to the health information, including:
processing the health information by adopting a synonym model trained and established in advance to acquire standard health information of the target user, wherein the synonym model is acquired by a natural language understanding method;
and acquiring a keyword mapped with the standard health information of the target user according to the mapping relation between the standard health information and the keyword, wherein the keyword is used as the keyword influencing the health state of the target user, and the mapping relation between the standard health information and the keyword is stored in a database in advance.
Optionally, the determining module 204 searches the ingredient information and/or the nutritional component information to determine whether there are ingredients and/or nutritional components matching the keyword, including:
converting the ingredient information into standard word information by adopting a synonym model trained and established in advance, wherein the synonym model is obtained by a natural language understanding method;
searching in standard word information and/or nutrient component information corresponding to the ingredient information, and judging whether ingredients and/or nutrient components matched with the keywords exist.
Optionally, the health information includes disease information and/or physical sign information of the user, where the disease information includes: the disease that the user has suffered from or the disease that the user is more concerned about suffering from, the sign information comprises: symptoms of recent discomfort and information on the sex, age, height, weight, heart rate, blood pressure, blood glucose, body fat rate of the user.
Optionally, the apparatus further comprises:
the setting module is used for setting a weight value through a weight setting model established by pre-training according to the sign information of the target user;
the calculation module is used for calculating the safe intake threshold of ingredients and/or nutritional ingredients influencing the health state of the target user in the food according to the weight value through a preset calculation formula;
a determination module for determining the edible amount of the food product by the target user according to the safe intake threshold value and the content of ingredients and/or nutritional components in the food product which affect the health state of the target user.
Optionally, the apparatus further comprises:
a prompt module for prompting the target user that the food item is inedible or inedible beyond the determined edible amount.
Optionally, the weight setting model is obtained by training with different disease information and sign information as condition inputs.
Optionally, the calculation formula is stored in a database, and is mapped and stored with corresponding disease information and/or physical sign information.
Optionally, the obtaining, by the determining module 204, health information of the target user includes:
acquiring health information of the target user through a health database, wherein the health database is established in the following way: identifying a physical examination report, a medical record report and/or a laboratory sheet uploaded by a user, establishing a health database after acquiring health information of the user, or establishing the health database after receiving the health information input by the user;
and/or receiving the health information input by the target user through a human-computer interaction interface;
and/or acquiring the health information of the target user through a wearable intelligent device worn by the target user.
Optionally, the region identification model is an attention model established by using an attention mechanism;
or, the region identification model is a convolutional neural network model.
Optionally, the character region recognition model is a Mask-RCNN model.
Optionally, the determining module 204 is further configured to:
judging whether the food contains the dietetic restraint components and/or the allergy information according to the ingredient information and/or the nutritional component information;
if so, prompting the target user for the presence of a dietetic composition and/or allergy information in the food.
An embodiment of the present invention further provides an electronic device, and fig. 4 is a schematic structural diagram of the electronic device according to the embodiment of the present invention. Referring to fig. 4, an electronic device includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 communicate with each other via the communication bus 304,
a memory 303 for storing a computer program;
the processor 301, when executing the program stored in the memory 303, implements the following steps:
acquiring a packaging picture of food to be identified, and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model;
identifying each line of character areas in the ingredient information area and/or the nutrient component information area through a character area identification model established by pre-training;
identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutritional ingredient information of the food;
and acquiring health information of a target user, and judging whether the food has a risk of influencing the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
For specific implementation and related explanation of each step of the method, reference may be made to the method embodiment shown in fig. 1, which is not described herein again.
In addition, other implementation manners of the method for identifying the packaged food, which are realized by the processor 301 executing the program stored in the memory 303, are the same as the implementation manners mentioned in the foregoing method embodiment portions, and are not described again here.
By applying the electronic equipment provided by the embodiment, the packaging picture of the food can be identified, the ingredient information and/or the nutritional ingredient information displayed on the food package can be obtained, whether the ingredient information and/or the nutritional ingredient information of the food contains ingredients which influence the health of the user is judged based on the health information of the user, and whether the food has risks which influence the health state of the user is further determined, so that the health prompt of the user can be performed.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware component.
An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned method for identifying a packaged food.
By applying the computer-readable storage medium provided by the embodiment, the packaging picture of the food can be identified, the ingredient information and/or the nutritional ingredient information displayed on the food package can be obtained, whether the ingredient information and/or the nutritional ingredient information of the food contains ingredients which influence the health of the user is judged based on the health information of the user, and whether the food has risks which influence the health state of the user is further determined, so that the health prompt of the user can be performed.
It should be noted that, in the present specification, all the embodiments are described in a related manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system, the electronic device, and the computer-readable storage medium embodiments, since they are substantially similar to the method embodiments, the description is simple, and for the relevant points, reference may be made to part of the description of the method embodiments.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (20)
1. A method for identifying a packaged food, comprising:
acquiring a packaging picture of food to be identified, and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model;
identifying each line of character areas in the ingredient information area and/or the nutrient component information area through a character area identification model established by pre-training;
identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutritional ingredient information of the food;
and acquiring health information of a target user, and judging whether the food has a risk of influencing the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
2. The method for identifying packaged food as claimed in claim 1, wherein the step of determining whether the food affects the health risk of the target user according to the ingredient information and/or the nutritional component information and the health information comprises:
determining keywords influencing the health state of the target user according to the health information;
searching in the ingredient information and/or the nutritional ingredient information, and judging whether ingredients and/or nutritional ingredients matched with the keywords exist or not;
if so, determining that the food product is at risk of affecting the health status of the target user;
if not, determining that the food is not at risk of affecting the health status of the target user.
3. The method for identifying packaged food as claimed in claim 2, wherein determining keywords affecting the health status of the target user according to the health information comprises:
processing the health information by adopting a synonym model trained and established in advance to acquire standard health information of the target user, wherein the synonym model is acquired by a natural language understanding method;
and acquiring a keyword mapped with the standard health information of the target user according to the mapping relation between the standard health information and the keyword, wherein the keyword is used as the keyword influencing the health state of the target user, and the mapping relation between the standard health information and the keyword is stored in a database in advance.
4. The method for identifying packaged food as claimed in claim 2, wherein searching the ingredient information and/or nutritional component information to determine whether there is an ingredient and/or nutritional component matching the keyword comprises:
converting the ingredient information into standard word information by adopting a synonym model trained and established in advance, wherein the synonym model is obtained by a natural language understanding method;
searching in standard word information and/or nutrient component information corresponding to the ingredient information, and judging whether ingredients and/or nutrient components matched with the keywords exist.
5. The method for identifying packaged food as claimed in claim 1, wherein the health information includes disease information and/or physical sign information of the user, wherein the disease information includes: the disease that the user has suffered from or the disease that the user is more concerned about suffering from, the sign information comprises: symptoms of recent discomfort and information on the sex, age, height, weight, heart rate, blood pressure, blood glucose, body fat rate of the user.
6. The method for identifying packaged food as claimed in claim 5, wherein the method further comprises:
setting a weight value through a weight setting model established by pre-training according to the sign information of the target user;
according to the weight value, calculating a safe intake threshold value of ingredients and/or nutritional ingredients influencing the health state of the target user in the food through a preset calculation formula;
determining the edible amount of the target user to the food according to the safe intake threshold value and the content of the ingredients and/or nutritional components influencing the health state of the target user in the food.
7. The method for identifying a packaged food item according to claim 6, further comprising:
prompting the target user that the food item is not edible, or is not edible beyond the determined edible amount.
8. The method for identifying packaged food according to claim 6, wherein the weight setting model is trained by using different disease information and sign information as condition inputs.
9. The method for identifying the packaged food as claimed in claim 6, wherein the calculation formula is stored in a database and is mapped and stored with the corresponding disease information and/or physical sign information.
10. The method for identifying packaged food as claimed in claim 1, wherein the obtaining of health information of the target user comprises:
acquiring health information of the target user through a health database, wherein the health database is established in the following way: identifying a physical examination report, a medical record report and/or a laboratory sheet uploaded by a user, establishing a health database after acquiring health information of the user, or establishing the health database after receiving the health information input by the user;
and/or receiving the health information input by the target user through a human-computer interaction interface;
and/or acquiring the health information of the target user through a wearable intelligent device worn by the target user.
11. The method for identifying a packaged food as claimed in claim 1, wherein the region identification model is an attention model established by an attention mechanism;
or, the region identification model is a convolutional neural network model.
12. The method for recognizing a packaged type food product according to claim 1, wherein the character region recognition model is a Mask-RCNN model.
13. The method for identifying a packaged food item according to claim 1, further comprising:
judging whether the food contains the dietetic restraint components and/or the allergy information according to the ingredient information and/or the nutritional component information;
if so, prompting the target user for the presence of a dietetic composition and/or allergy information in the food.
14. A packaging-type food identifying device, comprising:
the first identification module is used for acquiring a packaging picture of food to be identified and identifying an ingredient information area and/or a nutrient component information area from the packaging picture through a pre-trained and established area identification model;
the second recognition module is used for recognizing each line of character area in the ingredient information area and/or the nutrient component information area through a character area recognition model established by pre-training;
the third identification module is used for identifying characters in each line of character area through a character identification model so as to obtain ingredient information and/or nutrient component information of the food;
and the judging module is used for acquiring the health information of the target user and judging whether the food affects the risk of the health state of the target user according to the ingredient information and/or the nutritional ingredient information and the health information.
15. The packaged food identifying device of claim 14, wherein the determining module is specifically configured to:
determining keywords influencing the health state of the target user according to the health information;
searching in the ingredient information and/or the nutritional ingredient information, and judging whether ingredients and/or nutritional ingredients matched with the keywords exist or not;
if so, determining that the food product is at risk of affecting the health status of the target user;
if not, determining that the food is not at risk of affecting the health status of the target user.
16. The packaged food item identification device of claim 15, wherein the determining module determines keywords affecting the health status of the target user according to the health information, and comprises:
processing the health information by adopting a synonym model trained and established in advance to acquire standard health information of the target user, wherein the synonym model is acquired by a natural language understanding method;
and acquiring a keyword mapped with the standard health information of the target user according to the mapping relation between the standard health information and the keyword, wherein the keyword is used as the keyword influencing the health state of the target user, and the mapping relation between the standard health information and the keyword is stored in a database in advance.
17. The packaged food identifying device of claim 15, wherein the determining module searches the ingredient information and/or the nutritional component information to determine whether there is an ingredient and/or a nutritional component matching the keyword, and comprises:
converting the ingredient information into standard word information by adopting a synonym model trained and established in advance, wherein the synonym model is obtained by a natural language understanding method;
searching in standard word information and/or nutrient component information corresponding to the ingredient information, and judging whether ingredients and/or nutrient components matched with the keywords exist.
18. The packaged-type food item identification device of claim 14, wherein the health information comprises disease information and/or physical sign information of the user, wherein the disease information comprises: the disease that the user has suffered from or the disease that the user is more concerned about suffering from, the sign information comprises: symptoms of recent discomfort and information on the sex, age, height, weight, heart rate, blood pressure, blood glucose, body fat rate of the user.
19. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the program stored on the memory, implementing the method steps of any of claims 1-13.
20. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910975127.8A CN110718282A (en) | 2019-10-14 | 2019-10-14 | Packaging food identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910975127.8A CN110718282A (en) | 2019-10-14 | 2019-10-14 | Packaging food identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110718282A true CN110718282A (en) | 2020-01-21 |
Family
ID=69211653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910975127.8A Pending CN110718282A (en) | 2019-10-14 | 2019-10-14 | Packaging food identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110718282A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488920A (en) * | 2020-03-27 | 2020-08-04 | 浙江工业大学 | Bag opening position detection method based on deep learning target detection and recognition |
| CN111768820A (en) * | 2020-06-04 | 2020-10-13 | 上海森亿医疗科技有限公司 | Paper medical record digitization and target detection model training method, device and storage medium |
| CN112580690A (en) * | 2020-11-24 | 2021-03-30 | 南通大学 | Information processing method and device for improving food detection accuracy |
| CN112630458A (en) * | 2020-12-31 | 2021-04-09 | 佳力士添加剂（海安）有限公司 | Method and device for detecting quality of monoglyceride |
| CN113379015A (en) * | 2021-07-07 | 2021-09-10 | 深圳市伊欧乐科技有限公司 | Nutrient composition information analysis method and device, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424201A (en) * | 2013-08-21 | 2015-03-18 | 富士通株式会社 | Method and device for providing food safety information |
| CN104866849A (en) * | 2015-04-30 | 2015-08-26 | 天津大学 | Food nutrition label identification method based on mobile terminal |
| US20160154823A1 (en) * | 2010-06-30 | 2016-06-02 | International Business Machines Corporation | Template-based recognition of food product information |
| CN106407970A (en) * | 2016-08-31 | 2017-02-15 | 乐视控股（北京）有限公司 | Nutrient intake obtaining method and device |
| CN106777882A (en) * | 2016-11-18 | 2017-05-31 | 北京郁金香伙伴科技有限公司 | A kind of diet reminding method and device |
-
2019
- 2019-10-14 CN CN201910975127.8A patent/CN110718282A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160154823A1 (en) * | 2010-06-30 | 2016-06-02 | International Business Machines Corporation | Template-based recognition of food product information |
| CN104424201A (en) * | 2013-08-21 | 2015-03-18 | 富士通株式会社 | Method and device for providing food safety information |
| CN104866849A (en) * | 2015-04-30 | 2015-08-26 | 天津大学 | Food nutrition label identification method based on mobile terminal |
| CN106407970A (en) * | 2016-08-31 | 2017-02-15 | 乐视控股（北京）有限公司 | Nutrient intake obtaining method and device |
| CN106777882A (en) * | 2016-11-18 | 2017-05-31 | 北京郁金香伙伴科技有限公司 | A kind of diet reminding method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488920A (en) * | 2020-03-27 | 2020-08-04 | 浙江工业大学 | Bag opening position detection method based on deep learning target detection and recognition |
| CN111768820A (en) * | 2020-06-04 | 2020-10-13 | 上海森亿医疗科技有限公司 | Paper medical record digitization and target detection model training method, device and storage medium |
| CN112580690A (en) * | 2020-11-24 | 2021-03-30 | 南通大学 | Information processing method and device for improving food detection accuracy |
| CN112580690B (en) * | 2020-11-24 | 2021-12-07 | 南通大学 | Information processing method and device for improving food detection accuracy |
| CN112630458A (en) * | 2020-12-31 | 2021-04-09 | 佳力士添加剂（海安）有限公司 | Method and device for detecting quality of monoglyceride |
| CN112630458B (en) * | 2020-12-31 | 2021-11-12 | 佳力士添加剂（海安）有限公司 | Method and device for detecting quality of monoglyceride |
| CN113379015A (en) * | 2021-07-07 | 2021-09-10 | 深圳市伊欧乐科技有限公司 | Nutrient composition information analysis method and device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11672446B2 (en) | Insulin delivery recommendations based on nutritional information | |
| CN110718282A (en) | Packaging food identification method and device | |
| Liberali et al. | Dietary patterns and childhood obesity risk: a systematic review | |
| US20190295440A1 (en) | Systems and methods for food analysis, personalized recommendations and health management | |
| Sotos-Prieto et al. | Design and development of an instrument to measure overall lifestyle habits for epidemiological research: the Mediterranean Lifestyle (MEDLIFE) index | |
| CN109346153A (en) | It is a kind of to digitize system and method for having dinner | |
| US20150279235A1 (en) | Nutrition management system and nutrition management program | |
| CN110867239A (en) | Diet suggestion generation method and device, computer device and storage medium | |
| CN110853735A (en) | Method and device for analyzing intake of dietary component, computer device and storage medium | |
| CN113936774A (en) | Diet recommendation method, device, system, storage medium and electronic equipment | |
| WO2021044696A1 (en) | Device for estimating nutritional intake amount, health management assistance device, method for estimating nutritional intake amount, health management assistance method, program, and system for estimating nutritional intake amount | |
| CN107705837B (en) | Method, device and system for recommending selected food | |
| M. Silva et al. | Investigating preferred food description practices in digital food journaling | |
| Moursi et al. | There’s an app for that: development of an application to operationalize the global diet quality score | |
| Lustig | Metabolical: The Lure and the Lies of Processed Food, Nutrition, and Modern Medicine | |
| CN105286788A (en) | System and method for controlling diet in patient of chronic disease based on human characteristic data | |
| CN112133434A (en) | Dietary habit-based hyperlipidemia auxiliary diagnosis system, device and storage medium | |
| CN112331302A (en) | Automatic diet management method and system, kitchen robot and storage medium | |
| CN111159528B (en) | Questionnaire information pushing method and device, storage medium and electronic device | |
| BALINT et al. | The role of diet and lifestyle habits in prevention of cardiovascular diseases in Moldavian and Transylvanian population | |
| CN110910987A (en) | Diet advice generation method and apparatus, computer apparatus, and storage medium | |
| CN116453651A (en) | Diet evaluation method, diet evaluation device, computer equipment and computer readable storage medium | |
| Harvey et al. | Nutrition for a healthy pregnancy | |
| CN114388102A (en) | Diet recommendation method and device and electronic equipment | |
| CN112017755A (en) | Intelligent nutrition collocation recommendation method, system and robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |